Search Results

This Pulse Oximeter is intended for measuring the functional oxygen saturation (SpO2) and pulse rate (PR). It is intended for spot check of SpO2, PR of adult or pediatric patients (weight >=40kg) in home. This device is not intended for continuous monitoring. It is intended to be used by both lay person or healthcare professional in the home environment.

The Pulse Oximeter is intended for use in measuring and displaying functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate (PR). The Pulse Oximeter works by applying a sensor to a pulsating arteriolar vascular bed. The sensor contains a dual light source and photo detector. The one wavelength of light source is 660 nm, which is red light; the other is 905 nm, which is Infrared light. Skin, bone, tissue, and venous vessels normally absorb a constant amount of light over time. The photodetector in finger sensor collects and converts the light into electronic signal which is proportional to the light intensity. The arteriolar bed normally pulsates and absorbs variable amounts of light during systole and diastole, as blood volume increases and decreases. The ratio of light absorbed at systole and diastole is translated into an oxygen saturation measurement. This measurement is referred to as SpO2. The Pulse Oximeter is powered by 2 AAA alkaline batteries. The device mainly composed of PCB board, On/Off button, mode button, OLED&LED screen, battery compartment, and plastic shell. The device is a spot-check pulse oximeter and does not include alarms. The device is not intended for life-supporting or life-sustaining.

The provided FDA 510(k) summary for the Pulse Oximeter (Model: PO101, PO102, PO103) includes information about acceptance criteria and a study to demonstrate performance.

Here's a breakdown of the requested information:

1. A table of acceptance criteria and the reported device performance

Notes on the table:

• The document explicitly states the "SpO2 Accuracy" and "PR Accuracy" directly as acceptance criteria within the comparison table between the subject and predicate devices.
• The "Reported Device Performance" for these parameters is shown to match the acceptance criteria, indicating the device meets them.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Sample Size: Not explicitly stated in the provided document. The document mentions "human adult volunteers" for the clinical hypoxia test.
• Data Provenance: Not explicitly stated in the provided document. The manufacturer and correspondent are based in China, but the location of the clinical study is not specified. The study was prospective in nature as it involved deliberately inducing hypoxia in human volunteers.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Not applicable in this context. The "ground truth" for oxygen saturation (SpO2) in pulse oximetry studies is typically established by arterial blood gas analysis (co-oximetry), not by expert consensus. The document states: "Clinical hypoxia test results were obtained in human adult volunteers to validate the accuracy of Pulse Oximeter versus arterial oxygen saturation (SaO2) as determined by co-oximetry."

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• Not applicable. Adjudication methods like 2+1 or 3+1 are used in studies where human readers interpret medical images or data and their interpretations need to be reconciled to establish a consensus ground truth. In pulse oximetry, the gold standard (co-oximetry) is an objective measurement, not subject to interpretation requiring adjudication.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This type of study is relevant for AI-powered diagnostic tools where human readers are assisted by AI. The Pulse Oximeter is a standalone medical device that provides readings of SpO2 and PR, not an AI-assisted diagnostic tool for human interpretation.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

• Yes, a standalone performance study was done. The entire clinical study for the Pulse Oximeter is inherently a standalone performance evaluation, as the device itself is measuring SpO2 and PR, and its readings are compared against the gold standard (co-oximetry) without human interpretation in the loop impacting the device's measurement.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

• The ground truth used was arterial oxygen saturation (SaO2) as determined by co-oximetry. This is considered the gold standard for measuring oxygen saturation directly from arterial blood.

8. The sample size for the training set

• Not applicable. This device is a traditional medical device, not an AI/machine learning model that requires a "training set" in the computational sense. Its performance is based on its physical and optical design, algorithms for signal processing, and calibration during manufacturing.

9. How the ground truth for the training set was established

• Not applicable, as there is no "training set" in the context of this traditional medical device.

Ask a specific question about this device

Fetal Doppler is intended to detect fetal heart rate, and play the fetal heart sound. Fetal Doppler is indicated for use by health care professionals in hospital, clinic, community and home for singleton pregnancies after 12 weeks gestation.

Fetal Doppler is intended to detect fetal heart beats, display fetal heart rate, and play the fetal heart sound. Fetal Doppler is indicated for use by used by health care professionals in hospital, clinic, community and home for singleton pregnancies after 12 weeks gestation. It is comprised of an ultrasonic signal transmitter and receiver, analog signal processing unit, FHR calculating unit, and LCD/TFT display control unit. It has audio output and can be connected with headphones or to a recorder with audio input. The Fetal Doppler is powered by a standard 1.5 V DC alkaline battery.

This document seems to be a 510(k) summary for a Fetal Doppler device, not a study evaluating a device's performance against specific acceptance criteria in the way a clinical trial or algorithm validation study would. Therefore, much of the requested information regarding acceptance criteria for an AI/ML algorithm or a comparative effectiveness study is not available in the provided text.

The document instead focuses on demonstrating substantial equivalence to a predicate device through conformity with standards and basic performance tests.

Here's a breakdown of what is available and what is not:

1. A table of acceptance criteria and the reported device performance

The document does not provide a table with "acceptance criteria" and "reported device performance" in the context of an AI/ML algorithm's effectiveness. Instead, it outlines performance data provided to support substantial equivalence, primarily focusing on safety and basic operational characteristics.

Here's a summary of the performance testing conducted, which might be interpreted as meeting certain "acceptance criteria" for basic functionality:

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

This information is not provided in the document. The performance tests mentioned (biocompatibility, software V&V, electrical safety, use/battery life, acoustic output) are engineering tests, not typically clinical studies involving patient data or test sets in the context of an AI/ML algorithm.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

This information is not applicable/not provided. The document describes testing of a medical device's physical and software components, not an AI/ML algorithm requiring expert ground truth for a test set.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

This information is not applicable/not provided. As above, this document does not describe an AI/ML algorithm validation study that would involve expert adjudication of a test set.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

This information is not applicable/not provided. This document is for a Fetal Doppler, which is not an AI-assisted diagnostic device. Therefore, no MRMC study or AI assistance evaluation was conducted or reported.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

This information is not applicable/not provided. The Fetal Doppler is a standalone device; the question about "algorithm only" performance applies to AI/ML devices, which this is not. The device itself performs the function of detecting and displaying FHR.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

This information is not applicable/not provided. The "ground truth" for a Fetal Doppler would be the actual fetal heart rate, which is derived directly from its acoustic processing, not from expert consensus or pathology in a diagnostic sense. The accuracy of the FHR measurement is stated as ±2BPM.

8. The sample size for the training set

This information is not applicable/not provided. This device is not an AI/ML algorithm that requires a "training set."

9. How the ground truth for the training set was established

This information is not applicable/not provided. This device is not an AI/ML algorithm that requires a "training set" with ground truth.

Ask a specific question about this device